VISUAL AND MATHEMATICAL BASES FOR THE USE OF ARTIFICIAL INTELLIGENCE IN THE IDENTIFICATION OF FOUR SPECIES OF THE GENUS MUGIL
DOI:
https://doi.org/10.18817/repesca.v17i1.4426Keywords:
Inovação, Recursos pesqueiros, Pesca, Análise de imagem, Gestão pesqueiraAbstract
Accurate fish species identification is essential for sustainable fisheries management, aquatic biodiversity conservation, and the generation of reliable scientific data, particularly in coastal and estuarine environments where artisanal fisheries play a central role. However, taxonomic groups with high morphological similarity, such as the genus Mugil (Mugilidae), often present high misidentification rates when based solely on visual observation. Considering the limitations of molecular methods, which require high costs and specialized infrastructure, this study aimed to develop and present an integrated, accessible, and non-invasive approach to assist in the identification of Mugil species common along the Maranhão coast, using digital images and explanatory mathematical modeling. Images of Mugil brevirostris, Mugil curema, Mugil incilis, and Mugil liza were analyzed, from which basic morphometric measures (body area, maximum length, and maximum height) and proportional índices, such as Area Index, Aspect Ratio, and a scale regularity index based on brightness variation, were extracted. The integration of these descriptors enabled the construction of an interpretable mathematical model capable of logically differentiating the analyzed species, even within a morphologically cryptic group. The results demonstrated that visually perceptible characteristics can be translated into objective quantitative metrics, reducing the subjectivity of traditional morphological identification. The proposed methodology shows strong potential for applications in environmental education, participatory monitoring, citizen science, and fisheries management, while also establishing a conceptual foundation for future applications in artificial intelligence. It is concluded that the combination of visual analysis, digital morphometrics, and simple explanatory models represents an effective, understandable, and low-cost tool for the identification of coastal fish species.
References
BALLARD, H., LINDELL, A., & JADALLAH, C. (2024). Environmental education outcomes of community and citizen science: a systematic review of empirical research. Environmental Education Research, 30, 1007 - 1040. https://doi.org/10.1080/13504622.2024.2348702 DOI: https://doi.org/10.1080/13504622.2024.2348702
BANERJEE, A., DAS, A., BEHRA, S., BHATTACHARJEE, D., SRINIVASAN, N., NASIPURI, M., & DAS, N. (2022). Carp-DCAE: Deep convolutional autoencoder for carp fish classification. Comput. Electron. Agric., 196, 106810. https://doi.org/10.1016/j.compag.2022.106810 DOI: https://doi.org/10.1016/j.compag.2022.106810
BEKKOZHAYEVA, D., & CÍSAR̆, P. (2022). Image-Based Automatic Individual Identification of Fish without Obvious Patterns on the Body (Scale Pattern). Applied Sciences. https://doi.org/10.3390/app12115401 DOI: https://doi.org/10.3390/app12115401
BLANCO-FERNANDEZ, C., ERZINI, K., RODRÍGUEZ-DIEGO, S., ALBA-GONZALEZ, P., THIAM, N., SOW, F., DIALLO, M., VIÐARSSON, J., FERNÁNDEZ-VIDAL, D., GONÇALVES, J., RANGEL, M., STOBBERUP, K., GARCIA-VAZQUEZ, E., & MACHADO-SCHIAFFINO, G. (2022). Two Fish in a Pod. Mislabelling on Board Threatens Sustainability in Mixed Fisheries, 9. https://doi.org/10.3389/fmars.2022.841667 DOI: https://doi.org/10.3389/fmars.2022.841667
BOOKSTEIN, F. L. (1991) Morphometric tools for landmark data: geometry and biology. Cambridge: Cambridge University Press. https://doi.org/10.1017/CBO9780511573064 DOI: https://doi.org/10.1017/CBO9780511573064
CADRIN, S. (2000). Advances in morphometric identification of fishery stocks. Reviews in Fish Biology and Fisheries, 10, 91-112. https://doi.org/10.1023/a:1008939104413 DOI: https://doi.org/10.1023/A:1008939104413
COSTA, L. F.; CESAR JR., R. M. Shape Analysis and Classification: Theory and Practice. Boca Raton: CRC Press, 2009, 680 p. https://doi.org/10.1201/9781420037555 DOI: https://doi.org/10.1201/9781420037555
DURAND, J., SHEN, K., CHEN, W., JAMANDRE, B., BLEL, H., DIOP, K., NIRCHIO, M., LEÓN, F., WHITFIELD, A., CHANG, C., & BORSA, P. (2012). Systematics of the grey mullets (Teleostei: Mugiliformes: Mugilidae): molecular phylogenetic evidence challenges two centuries of morphology-based taxonomy.. Molecular phylogenetics and evolution, 64 1, 73-92. https://doi.org/10.1016/j.ympev.2012.03.006 DOI: https://doi.org/10.1016/j.ympev.2012.03.006
DURAND, J., HUBERT, N., SHEN, K., & BORSA, P. (2017). DNA barcoding grey mullets. Reviews in Fish Biology and Fisheries, 27, 233-243. https://doi.org/10.1007/s11160-016-9457-7 DOI: https://doi.org/10.1007/s11160-016-9457-7
FERREIRA, A., AZEVEDO, O., BARROSO, C., DUARTE, S., EGAS, C., FONTES, J., RÉ, P., SANTOS, A., & COSTA, F. (2024). Multi-marker DNA metabarcoding for precise species identification in ichthyoplankton samples. Scientific Reports, 14. https://doi.org/10.1038/s41598-024-69963-7 DOI: https://doi.org/10.1038/s41598-024-69963-7
FORTUNATO, R., GONZÁLEZ-CASTRO, M., GALÁN, A., ALONSO, I., KUNERT, C., DURÀ, V., & VOLPEDO, A. (2017). Identification of potential fish stocks and lifetime movement patterns of Mugil liza Valenciennes 1836 in the Southwestern Atlantic Ocean. Fisheries Research, 193, 164-172. https://doi.org/10.1016/j.fishres.2017.04.005 DOI: https://doi.org/10.1016/j.fishres.2017.04.005
FRAGA, E., SCHNEIDER, H., NIRCHIO, M., SANTA-BRIGIDA, E., RODRIGUES-FILHO, L., & SAMPAIO, I. (2007). Molecular phylogenetic analyses of mullets (Mugilidae, Mugiliformes) based on two mitochondrial genes. Journal of Applied Ichthyology, 23, 598-604. https://doi.org/10.1111/j.1439-0426.2007.00911.x DOI: https://doi.org/10.1111/j.1439-0426.2007.00911.x
FROESE, R. (2006) Cube law, condition factor and weight–length relationships: history, meta‐analysis and recommendations. Journal of Applied Ichthyology, 22(4), 241–253. https://doi.org/10.1111/j.1439-0426.2006.00805.x DOI: https://doi.org/10.1111/j.1439-0426.2006.00805.x
GONZALEZ, R. C.; WOODS, R. E. Digital Image Processing. 4. ed. New York: Pearson, 2018. Disponível em: https://www.cl72.org/090imagePLib/books/Gonzales,Woods-Digital.Image.Processing.4th.Edition.pdf
HARALICK, R. M.; SHANMUGAM, K.; DINSTEIN, I. (1973) Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6), 610–621. https://doi.org/10.1109/TSMC.1973.4309314 DOI: https://doi.org/10.1109/TSMC.1973.4309314
LECUN, Y., BENGIO, Y. & HINTON, G. (2015) Deep learning. Nature 521, 436–444. https://doi.org/10.1038/nature14539 DOI: https://doi.org/10.1038/nature14539
LIMMON, G., DELRIEU‐TROTTIN, E., PATIKAWA, J., RIJOLY, F., DAHRUDDIN, H., BUSSON, F., STEINKE, D., & HUBERT, N. (2020). Assessing species diversity of Coral Triangle artisanal fisheries: A DNA barcode reference library for the shore fishes retailed at Ambon harbor (Indonesia). Ecology and Evolution, 10, 3356 - 3366. https://doi.org/10.1002/ece3.6128 DOI: https://doi.org/10.1002/ece3.6128
LOUW, M., & SANFORD‐DOLLY, C. (2023). Learning to see, seeing to learn: Impacts of an online tool on volunteers' observational practices during aquatic macroinvertebrate identification. Science Education. https://doi.org/10.1002/sce.21834 DOI: https://doi.org/10.1002/sce.21834
LU, J., ZHANG, S., ZHAO, S., LI, D., & ZHAO, R. (2024). A Metric-Based Few-Shot Learning Method for Fish Species Identification with Limited Samples. *Animals : an Open Access Journal from MDPI*, 14. https://doi.org/10.3390/ani14050755 DOI: https://doi.org/10.3390/ani14050755
MARTÍ-PUIG, P., MANJABACAS, A., & LOMBARTE, A. (2020). Automatic Classification of Morphologically Similar Fish Species Using Their Head Contours. Applied Sciences. https://doi.org/10.3390/app10103408 DOI: https://doi.org/10.3390/app10103408
MENEZES, N. (1983). Guia prático para conhecimento e identificação das tainhas e paratis (pisces, Mugilidae) do litoral brasileiro. Revista Brasileira De Zoologia, 2, 1-12. https://doi.org/10.1590/s0101-81751983000100001 DOI: https://doi.org/10.1590/S0101-81751983000100001
MORALES-PULIDO, J., GALINDO-SÁNCHEZ, C., JIMÉNEZ‐ROSENBERG, S., BATTA-LONA, P., HERZKA, S., & ARTEAGA, M. (2024). A molecular approach to identify parrotfish (Sparisoma) species during early ontogeny.. Journal of fish biology. https://doi.org/10.1111/jfb.15921 DOI: https://doi.org/10.1111/jfb.15921
MUJTABA, D., & MAHAPATRA, N. (2021). Convolutional Neural Networks for Morphologically Similar Fish Species Identification. 2021 International Conference on Computational Science and Computational Intelligence (CSCI), 1553-1559. https://doi.org/10.1109/csci54926.2021.00303 DOI: https://doi.org/10.1109/CSCI54926.2021.00303
MUSTAFIDAH, H., SUWARSITO, S., SETIAWAN, R., & KARIM, A. (2025). Image-Based Classification of Freshwater Fish Species to Support Feed Recommendation Using Random Forest. JUITA: Jurnal Informatika. https://doi.org/10.30595/juita.v13i2.27358 DOI: https://doi.org/10.30595/juita.v13i2.27358
NEVES, J., NOLEN, Z., FABRÉ, N., MOTT, T., & PEREIRA, R. (2021). Genomic methods reveal independent demographic histories despite strong morphological conservatism in fish species. Heredity, 127, 323 - 333. https://doi.org/10.1038/s41437-021-00455-4 DOI: https://doi.org/10.1038/s41437-021-00455-4
RAUF, H., LALI, M., ZAHOOR, S., SHAH, S., REHMAN, A., & BUKHARI, S. (2019). Visual features based automated identification of fish species using deep convolutional neural networks. Comput. Electron. Agric., 167. https://doi.org/10.1016/j.compag.2019.105075 DOI: https://doi.org/10.1016/j.compag.2019.105075
RAJAN, R., DURAND, J., THOMAS, L., SIDHARTHAN, A., RAHMAN, M., XAVIER, B., & RAGHAVAN, R. (2023). Barcoding Mullets (Mugilidae): Genetic Characterization of Exploited Species in Southern Peninsular India. Diversity. https://doi.org/10.3390/d15121193 DOI: https://doi.org/10.3390/d15121193
ROSSOUW, E., VON DER HEYDEN, S., & PEER, N. (2025). Aquatic eDNA outperforms sedimentary eDNA for the detection of estuarine fish communities in subtropical coastal vegetated ecosystems. Journal of Fish Biology, 107, 520 - 534. https://doi.org/10.1111/jfb.70056 DOI: https://doi.org/10.1111/jfb.70056
RUSS, J. C. The Image Processing Handbook. 6. ed. Boca Raton: CRC Press, 2011, 885 p. https://doi.org/10.1201/b10720 DOI: https://doi.org/10.1201/b10720
SARKAR, B., BHAKTA, J., JANA, B., SARKAR, U., & SINGH, M. (2024). Molecular Identification and Barcoding of Some Fishes Collected from Coastal Regions of West Bengal, India for Fish Diversity Conservation. Thalassas: An International Journal of Marine Sciences, 41. https://doi.org/10.1007/s41208-024-00774-3 DOI: https://doi.org/10.1007/s41208-024-00774-3
SANTANA, T. C., CARVALHO NETA, R. N. F., FERNANDES, J. F. F., LOBATO, R. S., CASTRO, J. S., CASTRO, J. J. P., BARBOSA, J. M., TEIXEIRA, E. G. (2019) An illustrated guide to commercial teleost fishes from Upaon-Açu Island, Brazil [electronic book] – São Luís: EDUEMA, 118 p. : il. color. ISBN: 978-85-8227-224-4.
STRACHAN, N., NESVADBA, P., & ALLEN, A. (1990). Fish species recognition by shape analysis of images. Pattern Recognit., 23, 539-544. https://doi.org/10.1016/0031-3203(90)90074-u DOI: https://doi.org/10.1016/0031-3203(90)90074-U
STRAUSS, R. E.; BOOKSTEIN, F. L. (1982) The truss: body form reconstructions in morphometrics. Systematic Zoology, 31(2), 113–135. https://doi.org/10.2307/2413032 DOI: https://doi.org/10.1093/sysbio/31.2.113
TRAVERSO, F., AICARDI, S., BOZZO, M., ZINNI, M., AMAROLI, A., GALLI, L., CANDIANI, S., VANIN, S., & FERRANDO, S. (2024). New Insights into Geometric Morphometry Applied to Fish Scales for Species Identification. Animals: an Open Access Journal from MDPI, 14. https://doi.org/10.3390/ani14071090 DOI: https://doi.org/10.3390/ani14071090
TEJASWINI, H., PAI, M., & PAI, R. (2024). Automatic Estuarine Fish Species Classification System Based on Deep Learning Techniques. IEEE Access, 12, 140412-140438. https://doi.org/10.1109/access.2024.3468438 DOI: https://doi.org/10.1109/ACCESS.2024.3468438
THARWAT, A., HEMEDAN, A., HASSANIEN, A., & GABEL, T. (2018). A biometric-based model for fish species classification. Fisheries Research, 204, 324-336. https://doi.org/10.1016/j.fishres.2018.03.008 DOI: https://doi.org/10.1016/j.fishres.2018.03.008
THU, P., HUANG, W., CHOU, T., VAN QUAN, N., VAN CHIEN, P., LI, F., SHAO, K., & LIAO, T. (2019). DNA barcoding of coastal ray-finned fishes in Vietnam. PLoS ONE, 14. https://doi.org/10.1371/journal.pone.0222631 DOI: https://doi.org/10.1371/journal.pone.0222631
WALTON, L., QUINDAZZI, M., GAUTHIER, S., & STEVENS, C. (2025). Fish ID face-off: A comparison of genetic barcoding and otolith shape analysis for streamlining species identification of mesopelagic fishes. Fisheries Research. https://doi.org/10.1016/j.fishres.2024.107254 DOI: https://doi.org/10.1016/j.fishres.2024.107254
VIDELER, J. J. (1993). Fish Swimming. Springer Nature, 260 p.. https://doi.org/10.1007/978-94-011-1580-3 DOI: https://doi.org/10.1007/978-94-011-1580-3
VON DER HEYDEN, S. (2025). 'It's not much, but it's honest work': The status of environmental DNA analyses of fish biodiversity in southern Africa.. Journal of fish biology. https://doi.org/10.1111/jfb.70187 DOI: https://doi.org/10.1111/jfb.70187
WHITE, D. J.; SVENDSEN, J. C.; BECK, A. A.; HAKOYAMA, H. Measuring the cost of active swimming in fish by analyzing body motion from digital images. Journal of Experimental Biology, v. 209, p. 409–417, 2006.
XU, X., LI, W., & DUAN, Q. (2020). Transfer learning and SE-ResNet152 networks-based for small-scale unbalanced fish species identification. Comput. Electron. Agric., 180, 105878. https://doi.org/10.1016/j.compag.2020.105878 DOI: https://doi.org/10.1016/j.compag.2020.105878
YANG, L., LIU, Y., YU, H., FANG, X., SONG, L., LI, D., & CHEN, Y. (2020). Computer Vision Models in Intelligent Aquaculture with Emphasis on Fish Detection and Behavior Analysis: A Review. Archives of Computational Methods in Engineering, 28, 2785 - 2816. https://doi.org/10.1007/s11831-020-09486-2 DOI: https://doi.org/10.1007/s11831-020-09486-2
ZHANG, D.; LU, G. (2004) Review of shape representation and description techniques. Pattern Recognition, v. 37, n. 1, p. 1–19, 2004. https://doi.org/10.1016/j.patcog.2003.07.008 DOI: https://doi.org/10.1016/j.patcog.2003.07.008
ZION, B. (2012) O uso de tecnologias de visão computacional na aquicultura — Uma revisão. Computadores e Eletrônica na Agricultura, 88, 125-132. https://doi.org/10.1016/j.compag.2012.07.010 DOI: https://doi.org/10.1016/j.compag.2012.07.010
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Revista Brasileira de Engenharia de Pesca
This work is licensed under a Creative Commons Attribution 4.0 International License.
